[Quantization] Enable compressed-tensors AWQ for Turing GPU (#29732)

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-11-30 14:04:28 +08:00
parent a491b0911b
commit e1464c3a08
1 changed files with 2 additions and 2 deletions
--- a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_wNa16.py
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_wNa16.py
@@ -79,8 +79,8 @@ class CompressedTensorsWNA16(CompressedTensorsScheme):

    @classmethod
    def get_min_capability(cls) -> int:
-        # ampere and up
-        return 80
+        # Turing and up
+        return 75

    def create_weights(
        self,